© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 27571
    Prev
    Next
    INDEX
    Explanations

    increasingly and its trends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izable
    -0.11
    çĶŁäº§æĢ»åĢ¼
    -0.10
    éħª
    -0.09
    izen
    -0.09
    æĽ¾ç»ı
    -0.08
    ãģĤãĤĭç¨ĭ度
    -0.08
    ä¸įæĸŃåĪĽæĸ°
    -0.08
    佬
    -0.08
    累累
    -0.08
    ä¸Ŀ毫ä¸į
    -0.08
    POSITIVE LOGITS
    ly
    0.12
    anko
    0.12
    ingly
    0.11
    дж
    0.11
    æľīç½ijåıĭ
    0.11
    ément
    0.10
     importantly
    0.10
    å¤ļåľ°
    0.09
    æį
    0.09
    mente
    0.09
    Activations Density 0.030%

    No Known Activations